Update README.md

q6_k: Uses Q8_K for all tensors

(Trained with Unsloth)

(Trained with Unsloth)

Update README.md

Update README.md

Update README.md

Update README.md

Create config.json

Delete config.json

q4_k_m: Recommended. Uses Q6_K for half of the attention.wv and feed_forward.w2 tensors, else Q4_K

Update README.md

Update README.md

(Trained with Unsloth)

(Trained with Unsloth)

Upload README.md with huggingface_hub

initial commit